← All skills
hugging-face-evaluation
82 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By ratnesh-maurya/cursor-claude-personas (GitHub) · coding · 12 stars · scanned at commit 975ca54
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 28 places.
Show 17 more
- ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 157
uv run scripts/evaluation_manager.py inspect-tables --repo-id "username/model" - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 189
AA_API_KEY="your-api-key" uv run scripts/evaluation_manager.py import-aa \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 198
echo "AA_API_KEY=your-api-key" >> .env - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 210
uv run scripts/evaluation_manager.py import-aa \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 223
HF_TOKEN=$HF_TOKEN \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 233
HF_TOKEN=$HF_TOKEN \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 243
uv run scripts/run_eval_job.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 270
uv run scripts/lighteval_vllm_uv.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 294
hf jobs uv run scripts/lighteval_vllm_uv.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 332
uv run scripts/inspect_vllm_uv.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 351
hf jobs uv run scripts/inspect_vllm_uv.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 373
uv run scripts/run_vllm_eval_job.py \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 406
uv run scripts/evaluation_manager.py --help - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 412
uv run scripts/evaluation_manager.py inspect-tables --repo-id "username/model-name" - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 417
uv run scripts/evaluation_manager.py extract-readme \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 429
AA_API_KEY=... uv run scripts/evaluation_manager.py import-aa \ - ai-ml-engineer/.claude/skills/hugging-face-evaluation/SKILL.md, line 438
uv run scripts/evaluation_manager.py show --repo-id "username/model-name"
and 8 more places
Downloads and installs other software
The author does not mention this.
Found in 1 place.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hugging-face-evaluation' ] || [ -L ~/.agents/skills/'hugging-face-evaluation' ]; then echo 'A skill folder named hugging-face-evaluation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ratnesh-maurya/cursor-claude-personas' "$d" && git -C "$d" checkout --quiet '975ca54f3da3ac38a3d9b4b5673e83271d8e3495' -- 'ai-ml-engineer/.claude/skills/hugging-face-evaluation' && mkdir -p ~/.agents/skills && cp -R "$d"/'ai-ml-engineer/.claude/skills/hugging-face-evaluation' ~/.agents/skills/'hugging-face-evaluation' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'hugging-face-evaluation' ~/.claude/skills/'hugging-face-evaluation' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for ratnesh-maurya/cursor-claude-personas shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/ratnesh-maurya/cursor-claude-personas/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | 975ca54 | 82 |
Also found in
Identical copies of this skill exist at:
- ratnesh-maurya/cursor-claude-personas/ai-ml-engineer/.cursor/skills/hugging-face-evaluation